mlr3torch

mlr3torch copied to clipboard

sebffischer

Before implementing the learner. Just build it as a Graph. The graph consists of: 1. Two input nodes (one for tokenization of categoricals, one for numerics). Need to maybe handle...

sebffischer

sebffischer

sebffischer

Go through the callback list in `luz` and see what we also want: https://mlverse.github.io/luz/reference/index.html#callbacks

sebffischer

When we define a lazy tensor and preprocess it, there should be a simple way to visualize the resulting tensors as images to check whether the preprocessing is applied correctly...

sebffischer

Bumps [actions/checkout](https://github.com/actions/checkout) from 5 to 6. Release notes Sourced from actions/checkout's releases. v6.0.0 What's Changed Update README to include Node.js 24 support details and requirements by @​salmanmkc in actions/checkout#2248 Persist...

dependabot[bot]

sebffischer

fix batch_size param

5

#420 Need to add tests I still think the `batch_size` parameter should be required for prediction.

sebffischer

missing batch_size error inconsistent with torch docs, batch_sampler arg

2

`?torch::dataloader` says ``` batch_sampler: (Sampler, optional): like sampler, but returns a batch of indices at a time. Mutually exclusive with ‘batch_size’, ‘shuffle’, sampler, and ‘drop_last’. Custom samplers can be created...

tdhock